Vehicle-mounted Doppler radar detection system, array and method

Abstract

The present invention discloses a vehicle-mounted Doppler radar detection system, a detection array and a detection method, which are used to detect the current health status of locomotives, tracks and roadbeds and their long-term change trends. The detection system includes a radar transmitting and receiving module and a main detection module. The radar transmitting and receiving module can be fixed to a rail vehicle and move along the track with the rail vehicle, and is used to transmit a radar beam to the track and receive a radar beam reflection signal during movement along the track. The detection module is used to process the radar beam reflection signal to obtain the Doppler characteristic information of the radar beam reflection signal according to the Doppler effect of each radar reflection beam, and judge the state of the detection target according to the Doppler characteristic information. The present invention installs the transmitting and receiving module of the Doppler radar on the rail vehicle and moves with the vehicle, without the need for a drone to follow the detection, thereby lowering the detection threshold, being easy to use and having high detection efficiency.

Description

Technical Field

[0001] The present invention relates to the field of rail transit detection, and in particular to a vehicle-mounted Doppler radar detection system, a detection array and a detection method, which are used to detect the running state of rail vehicles or the health state of tracks and roadbeds. Background Art

[0002] With the construction of high-speed railways and the development of urban subway transportation, rail transportation is becoming more and more popular. The gusset fasteners and threaded spikes of the track are one of the key components of the track system, which is related to the driving safety of the vehicles in the entire track system. The loss and displacement of gusset fasteners and threaded screws will cause driving hazards. In addition, abnormal movements and foreign objects on the foundation and track will also cause safety hazards for locomotive operation.

[0003] In traditional rail transit, the above-mentioned safety hazards mainly occur during the nighttime maintenance window period, which relies on manual inspection and maintenance of vehicle operations. This consumes a lot of manpower and material resources, sacrifices operational efficiency, and is prone to false detections and missed detections.

[0004] The existing system to supplement manual inspection has a method of fault diagnosis by collecting pictures and analyzing them. Its disadvantages are: 1. The detection effect depends on the image quality, especially when encountering bad weather, the image quality is poor, which is easy to lead to misjudgment; 2. The accuracy of the image analysis algorithm is high; 3. The use of images leads to a large data throughput of transmission and high requirements for channels; 4. Inspection operations need to be carried out during the maintenance window period specified by the track, and it is impossible to discover and troubleshoot related fault hazards of the track and roadbed during the normal operation of the locomotive.

[0005] The Chinese invention patent No. 201910168959.9 (authorization announcement No. CN109870683B) provides a method for detecting abnormal rail fasteners based on time-frequency feature analysis of radar signals. The method collects data by using a drone equipped with a 24GHz continuous wave radar. The drone patrols along the rails and emits a 24GHz continuous wave signal when it reaches the position above the rail fasteners. It collects echo data before, during and after the train passes, and compares the time-frequency spectrum of the fastener to be detected with the time-frequency spectrum of the corresponding category in the database. Figure 1A comparison is made to determine whether the rail fasteners are abnormal through the difference in the time-frequency spectrum. However, this technology requires the collection of radar echo data before, during and after the train passes, and the drone needs to stay obliquely above the fasteners for 1 to 15 seconds. This requires the drone to be controlled to follow the vehicle in movement. The use of drones may affect the safe operation of the train, and the cost of drones is high, and they cannot be used for long distances, causing inconvenience in operation. Moreover, this technology detects changes in the fasteners of a vehicle passing through the front and rear rail fixing points, and cannot monitor the current health status of the locomotive and the tracks and roadbeds along its line and their long-term change trends. In addition, this technology uses a single radar, and the single signal source leads to low detection accuracy. Summary of the invention

[0006] 1. Technical issues to be resolved

[0007] On one hand, the present invention aims to solve the problem that the track detection method based on image detection is prone to misjudgment and has low detection efficiency.

[0008] Another aspect of the present invention is to solve the problems of high cost, inability to use over long distances, and inconvenient operation when a drone follows a train to perform radar detection.

[0009] The third aspect of the present invention aims to solve the problem that the existing radar detection technology is unable to monitor the current health status and long-term change trend of the locomotive and the tracks and roadbed along its route.

[0010] The fourth aspect of the present invention aims to solve the problem of low detection accuracy of existing single radar detection technology.

[0011] (II) Technical solution

[0012] In order to solve the above technical problems, the present invention proposes a vehicle-mounted Doppler radar detection system, which is characterized by comprising: a radar transmitting and receiving module, which can be fixed on a rail vehicle and move along the track with the rail vehicle, and is used to transmit a radar beam to the track and receive a radar beam reflection signal during the movement along the track; a detection module, which is used to process the radar beam reflection signal to obtain Doppler characteristic information of the radar beam reflection signal according to the Doppler effect of each radar reflection beam, and judge the state of the detection target according to the Doppler characteristic information.

[0013] According to a preferred embodiment of the present invention, the Doppler characteristic information is obtained by comparing the current radar beam reflection signal with the standard radar beam signal.

[0014] According to a preferred embodiment of the present invention, the detection module includes a signal processing submodule and a feature analysis submodule, the signal processing submodule is used to preprocess the radar beam reflection signal to generate radar data; the feature analysis submodule is used to analyze the radar data to obtain the Doppler feature information, and judge the state of the detection target based on the Doppler feature information.

[0015] According to a preferred embodiment of the present invention, the detection module and the radar transmitting and receiving module are integrated into the same device, which is fixed to the rail vehicle and moves along the track with the rail vehicle.

[0016] According to a preferred embodiment of the present invention, the vehicle-mounted Doppler radar detection system includes a radar detection device and a state analysis device that can exchange information with each other, the signal processing submodule and the radar transmitting and receiving module are integrated in the radar detection device, and the radar detection device is fixed to the rail vehicle and moves along the track with the rail vehicle; the feature analysis submodule is integrated in the state analysis device.

[0017] According to a preferred embodiment of the present invention, the status analysis device is a cloud server.

[0018] According to a preferred embodiment of the present invention, the radar detection device and the state analysis device both include a communication module, so that the radar detection device and the state analysis device communicate with each other through the communication module.

[0019] According to a preferred embodiment of the present invention, there are at least two radar detection devices, which constitute a radar detection array; and the state analysis device can communicate with each radar detection device in the radar detection array through the communication module.

[0020] According to a preferred embodiment of the present invention, the radar detection device is further integrated with an antenna module, which serves as an antenna of the radar transmitting and receiving module.

[0021] According to a preferred embodiment of the present invention, when the radar detection device is used to form a radar detection array, the antenna module is a MIMO antenna module.

[0022] According to a preferred embodiment of the present invention, the detection module further comprises an inertial navigation sensor submodule, which is used to detect real-time position information of the radar detection device relative to the rail, and the real-time position information is used by the signal processing submodule to calibrate the radar data in real time.

[0023] According to a preferred embodiment of the present invention, the feature analysis submodule processes the Doppler feature information according to a trained deep learning model to calculate the state information of the measured object.

[0024] According to a preferred embodiment of the present invention, the deep learning model is obtained by collecting radar data from multiple radar detection devices on multiple trains and training feature data on the health status of rails and roadbeds generated based on the respectively collected data.

[0025] According to a preferred embodiment of the present invention, the signal processing submodule is also used to extract auxiliary feature information based on the radar beam reflection signal received by the radar transmitting and receiving module; the feature analysis submodule determines the state of the detection target based on the Doppler feature information and the auxiliary feature information.

[0026] According to a preferred embodiment of the present invention, the radar detection device is further integrated with a storage module, which is used to store the radar beam reflection signal and / or radar data generated by the radar beam reflection signal.

[0027] According to a preferred embodiment of the present invention, the radar detection device is also integrated with a main control module, which is used to control the operations of other modules.

[0028] According to a preferred embodiment of the present invention, the radar detection device is further integrated with a power management module, which is used to provide power to each module in the radar detection device.

[0029] A second aspect of the present invention provides a vehicle-mounted Doppler radar detection array, which is composed of a plurality of radar detection devices installed on the same rail vehicle, wherein the radar detection device is the radar detection device mentioned above.

[0030] A third aspect of the present invention provides a vehicle-mounted Doppler radar detection method, comprising: fixing a radar transmitting and receiving module on a rail vehicle and moving it along a track with the rail vehicle, transmitting a radar beam to the track and receiving a radar beam reflection signal during movement along the track; processing the radar beam reflection signal to obtain Doppler characteristic information of the radar beam reflection signal according to the Doppler effect of each radar reflection beam, and judging the state of the detection target according to the Doppler characteristic information.

[0031] According to a preferred embodiment of the present invention, the radar transmitting and receiving modules are radar transmitting and receiving modules from multiple radar detection devices, and the radar beam reflection signals are array signals received by the multiple radar transmitting and receiving modules.

[0032] According to a preferred embodiment of the present invention, the Doppler characteristic information is obtained by comparing the current radar beam reflection signal with the standard radar beam signal.

[0033] According to a preferred embodiment of the present invention, judging the state of the detection target according to the Doppler characteristic information includes: using a trained deep learning model to process the Doppler characteristic information to judge the state of the detection target.

[0034] According to a preferred embodiment of the present invention, the deep learning model is obtained by collecting radar data from multiple radar detection devices on multiple trains and training feature data on the health status of rails and roadbeds generated based on the respectively collected data.

[0035] (III) Beneficial effects

[0036] The present invention utilizes the Doppler effect of radar to achieve high-speed detection of moving targets in the radial direction of the radar aperture. Combined with the characteristics of the rails, it can be used, but not limited to, to monitor and locate the track health status of the plate fasteners, nuts and screws on the track, the loss, displacement, track loss, foreign objects and abnormal movement on the track on a high-speed train.

[0037] Compared with the image detection method, the present invention realizes the health status detection of tracks and foundations without images. The main advantages are: 1. It is independent of image quality and can ensure the detection effect in any weather conditions; 2. It can complete the inspection while the high-speed rail and subway are running, without the need for separate devices, equipment, or even manual inspection.

[0038] Compared with radar detection by drones following trains, the present invention installs the transmitting and receiving modules of Doppler radar on rail vehicles and moves with them, without the need for drones to follow the detection, which lowers the detection threshold, is easy to use and has high detection efficiency. In addition, the present invention can monitor the current health status and long-term change trend of the tracks and roadbeds along the locomotive and its line. In addition, the radar detection device of the present invention can form an array, and the radar array signal can improve the detection accuracy of the target. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a simplified diagram of the functional modules of the vehicle-mounted Doppler radar detection system of the present invention.

[0040] Figure 2 It is a schematic diagram of the module architecture of the first embodiment of the vehicle-mounted Doppler radar detection system of the present invention.

[0041] Figure 3 Schematic diagram of the module architecture of the second embodiment of the vehicle-mounted Doppler radar detection system of the present invention.

[0042] Figure 4 Schematic diagram of the module architecture of the third embodiment of the vehicle-mounted Doppler radar detection system of the present invention.

[0043] Figure 5 1 is a schematic diagram of the module architecture of the fourth embodiment of the vehicle-mounted Doppler radar detection system of the present invention.

[0044] Figure 6It is an overall structural diagram of an embodiment of a vehicle-mounted Doppler radar detector of the present invention.

[0045] Figure 7 It is an exploded view of the internal structure of an embodiment of a vehicle-mounted Doppler radar detector of the present invention.

[0046] Figure 8 It is a cross-sectional view of an embodiment of a vehicle-mounted Doppler radar detector of the present invention installed at the bottom of a train and above a rail.

[0047] Fig. 9 The present invention is a schematic diagram of a fault in which a track plate rotates due to loosening of a track nail nut in an embodiment of the vehicle-mounted Doppler radar detector of the present invention.

[0048] Fig.10 It is a detection flow diagram of the vehicle-mounted Doppler radar detection system of the present invention.

[0049] Fig.11 It is a schematic diagram of the array calculation example flow of the vehicle-mounted Doppler radar detection system of the present invention.

[0050] Fig.12 The present invention is a schematic diagram of the whole installation of the vehicle-mounted Doppler radar detection system. Implementation

[0051] Hereinafter, the vehicle-mounted Doppler radar detection device, array and method of the present invention will be described in detail in conjunction with exemplary embodiments. In the drawings, the same elements are marked with the same reference numerals.

[0052] Detailed illustrative embodiments are disclosed in the present invention. However, for the purpose of describing the exemplary embodiments, the specific structural and functional details disclosed in the present invention are merely representative. However, the present invention can be implemented in many alternative forms and should not be construed as being limited to the embodiments set forth in the present invention.

[0053] Therefore, although the example embodiments are capable of various modifications and alternative forms, these embodiments are shown in the accompanying drawings by way of example and are described in detail herein. However, it should be understood that the example embodiments should not be limited to the specific forms disclosed. On the contrary, the example embodiments cover all modifications, equivalents and alternatives falling within the scope of the present disclosure. In the entire description of the accompanying drawings, the same reference numerals represent the same elements.

[0054] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0055] Although the terms "first", "second", etc. can be used to describe various elements in the present invention, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, without departing from the scope of the present disclosure, the first element can be referred to as the second element, and similarly, the second element can be referred to as the first element. As used herein, the term "and / or" includes all any combinations of one or more of the related enumerated items.

[0056] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", and "combined" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be directly connected, or indirectly connected through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0057] The terms used in the present invention are only for the purpose of describing specific embodiments and should not be restrictive. As used in the present invention, the singular forms "one", "a kind of" and "the" should also include plural forms, unless otherwise clearly stated in the context. It will be further understood that the terms "include", "comprise", "contain", and / or "have" specify the presence of the features, wholes, steps, operations, elements and / or components when used in the present invention, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their collections. In the description of the present invention, unless otherwise stated, the meaning of "multiple" is two or more.

[0058] It should also be noted that in some alternative embodiments, the functions / actions indicated may not occur in the order indicated in the figures. For example, two figures shown in succession may in fact be performed substantially simultaneously, or may sometimes be performed in reverse order, depending on the functions / actions involved.

[0059] Specific details are provided in the following description to provide a thorough understanding of the example embodiments. However, one of ordinary skill in the art will appreciate that the example embodiments may be practiced without these specific details. For example, the system may be shown in a block diagram so as not to obscure the example embodiments in unnecessary detail. In other cases, well-known processes, structures, and techniques may be shown without unnecessary detail so as to avoid obscuring the example embodiments.

[0060] In the following description, illustrative embodiments will be described with respect to actions, and symbolic representations of operations that may be implemented as program modules or functional processes (e.g., in the form of flowcharts, flow charts, data flow diagrams, structure diagrams, block diagrams, etc.) include subroutines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types and may be implemented using existing hardware in existing network elements. Such existing hardware may include one or more central processing units (CPUs), digital signal processors (DSPs), application specific integrated circuits, field programmable gate arrays (FPGAs), computers, etc.

[0061] Although the flow chart may describe the operations as a sequential process, many of the operations may be performed in parallel, concurrently, or simultaneously. In addition, the order of the operations may be rearranged. A process may terminate when its operations are completed, but may also have additional steps not included in the figure. A process may correspond to a method, function, procedure, subroutine, subprogram, etc. When a process corresponds to a function, its termination may correspond to the function returning to the calling function or main function.

[0062] In order to solve the shortcomings of the existing image information-based detection of the health status of vehicles, tracks and roadbeds, the present invention proposes a vehicle-mounted Doppler radar detection system, which uses the Doppler effect of electromagnetic wave transmission to detect relevant detection targets in rail vehicles and their tracks. Different from the existing drone follow-up detection method, the present invention proposes to fix the radar transmitting and receiving module on the rail vehicle and move along the track with the rail vehicle, and directly process the radar beam reflection signal (echo signal) to determine whether the detection target is abnormal. Since there is no need to use a drone, it can be used even if some rail transportation cannot be followed by a drone, thus greatly broadening the application scenarios of radar detection. Moreover, since the detection device is directly fixed on the rail vehicle, the track can be fully detected without worrying about the problem of limited cruising range during drone detection. The radar transmitting and receiving module can be a radar transmitting and receiving module from multiple radar detection devices, so that the radar beam reflection signal can be an array signal received by multiple radar transmitting and receiving modules.

[0063] Figure 1 Schematic diagram of the functional modules of the vehicle-mounted Doppler radar detection system of the present invention. Figure 1 As shown, specifically, the vehicle-mounted Doppler radar detection system of the present invention at least includes a radar transmitting and receiving module 10 and a detection module 20. The radar transmitting and receiving module 10 is fixed to the rail vehicle and moves along the track with the rail vehicle, and is used to transmit a radar beam to the track and receive a radar beam reflection signal during the movement along the track. The detection module 20 is used to process the radar beam reflection signal to obtain the Doppler characteristic information of the radar beam reflection signal according to the Doppler effect of each radar reflection beam, and judge the state of the detection target according to the Doppler characteristic information. The detection module 20 can also include other signal detection and processing functions to help correctly complete the extraction of the above-mentioned Doppler characteristic information, such as but not limited to the signal detection and processing of the inertial navigation sensor module, so as to calibrate or deduct the influence of the vibration deviation on the radar signal during the vehicle's travel in real time. It should be noted that the "module" here is a functional entity, which can be implemented by hardware, software, or hardware with relevant software written in it. In specific implementation, the radar transmitting and receiving module 10 and the detection module 20 can be integrated into a single module or two independent modules. Alternatively, the functional part of the detection module that needs to process a large amount of data can be implemented as an independent module or device, which will be explained in the subsequent embodiments.

[0064] Furthermore, the present invention processes the radar beam reflection signal to obtain Doppler characteristic information of the signal generated by the Doppler effect, and analyzes the Doppler characteristic information to obtain the state of the relevant detection target, and the Doppler characteristic information is obtained by comparing the current radar beam reflection signal with the standard radar beam signal.

[0065] As a preferred implementation, when determining the detection target based on the Doppler characteristic information, machine learning technology is used for modeling, and the Doppler characteristic information is processed using the trained machine learning model to determine the state of the detection target.

[0066] Figure 2 FIG. 1 is a schematic diagram of the module architecture of the first embodiment of the vehicle-mounted Doppler radar detection system of the present invention. Figure 2 As shown, the vehicle-mounted Doppler radar detection system of the first embodiment is integrated into a single device (device). In addition to the radar transmitting and receiving module 10 and the detection module 20, the device also includes a storage module 30, a main control module 40, a power management module 50 and an antenna module 60.

[0067] The power management module 50 is used to provide the energy required by the radar transmitting and receiving module 10, the detection module 20, the storage module 30, the main control module 40 and the antenna module 60. The input power of the power management module 50 can be an external power supply, such as AC power, an external battery, etc.; it can also be a built-in battery, such as a lithium battery, etc. Of course, the input power supply can also include both an external power supply and a built-in battery. The external power port can use various industry-level DC-Jack mechanical structures or but not limited to any one of USB, MicroUSB, USB Type C and other mechanical structures. The built-in battery provides power when the external power supply cannot supply power normally.

[0068] The main control module 40 is used to control and manage various functional modules in the device, including the radar transmitting and receiving module 10, the detection module 20, the storage module 30, the power management module 50 and the antenna module 60. The main control module 40 can be composed of one or more CPUs, MCUs, FPGAs, DSPs and other components with control or digital processing functions. For example, the main control module 40 can be one or more microprocessors.

[0069] The main control module 40 can also be used to manage data from the detection module 20. As a specific implementation, the main control module 40 can enable the radar receiving and transmitting module 10 and the antenna module 60 to collect radar beam reflection signals, and enable the detection module 20 to perform signal processing to obtain processing results (detection target status data) or intermediate processing data, and store the radar beam reflection signals, processing result data (detection target status data) and / or intermediate processing result data in the storage module 30.

[0070] In addition, the main control module 40 can also compare the collected processing result data (detection target status data) with the data stored in the local storage module 30 to determine whether the monitored track facilities and foundation health status are normal. The signal containing the judgment result may include whether the monitored track facilities and foundation health are in a normal or abnormal normal operation state. For example, when the monitored track facilities are in an abnormal state, an alarm signal can be sent. The alarm signal includes but is not limited to abnormal state information of the monitored track facilities, rail defects, missing spikes, loose or missing spike nuts, displacement or missing track buckle plates, etc.

[0071] The memory space of the storage module 30 is allocated between the main control module 40, the power management module 101, the detection module 20, the radar receiving and transmitting module 10, and the antenna module 60, supporting each functional module to complete its function. The storage module 30 can be, but is not limited to, a NAND Flash Memory, a memory card, or a mini-SD / T-Flash / RS-MMC or other memory with read-write functions.

[0072] The detection module 20 has data processing functions, such as digital-to-analog converter (ADC) functions, digital signal processing functions, and security management functions. The ADC converts the received signal into a digital signal; the digital signal processing function is usually a digital signal processor (DSP), which is used for but not limited to operations such as Fast Fourier Transform (FFT), logarithmic amplitude, and memory compression; the data and device security management function is to generate device-specific keys for the processing module or its services when necessary to ensure the security of the device and data.

[0073] The radar transmitting and receiving module 10 includes a frequency modulated continuous wave radar transceiver (Frequency Modulated Continuous Wave, FMCW), a transceiver integrated feedback control circuit (abbreviated as: phase-locked loop (PLL, Phase-Locked Loop)), a transmitter, and a receiver. This embodiment can transmit and receive coverage from 76GHz to 81GHz, has an available bandwidth of 5GHz, and has multiple receiving channels and multiple transmitting channels. Each channel has a PCB antenna interface and a phase shifter for each transmission, and also includes an ultra-precise linear frequency modulation pulse engine based on fractional N PLL.

[0074] The antenna module 60 of this embodiment supports complex DDMA (Doppler diversity transmission) waveforms. Through simultaneous transmission of multiple antennas of DDMA and combined with the detection signal chain of the radar transmit and receive module 10, it can obtain a higher SNR (signal-to-noise ratio) and a longer detection distance than the commonly used TDMA (time diversity transmission) waveform, thereby comprehensively improving the performance of the radar.

[0075] The radar detection device of this embodiment can constitute a radar detection array, whereby the antenna module is a MIMO antenna module, which increases the number of virtual channels of the radar through MIMO (multiple input multiple output) technology, thereby improving the angular resolution of the radar. NTx Transmitting antennas, NRx A radar system with a receiving antenna can form a NTx × NRx The virtual antenna array increases the number of (virtual) antennas, thereby improving the angular resolution. This embodiment uses the waveform design technology of MIMO radar. Simply put, in order to form a virtual antenna array, the transmitter must be able to NTx The waveforms of the root transmitting antennas are multiplexed. After receiving this waveform, the receiving end must be able to convert it into NTxThe waveforms of the root transmitting antennas are separated. According to the selection of the multiplexing / separation dimension in the waveform design, the waveform of the MIMO radar in this embodiment adopts DDMA (Doppler Dimension Multiple Access). Under the DDMA waveform, all transmitting antennas transmit simultaneously, but the signal of each transmitting antenna is offset by a specific frequency. Through this artificially offset frequency, the signals of different transmitting antennas can be separated in the Doppler domain. Under the DDMA waveform, the speed values ​​detected in the echoes formed by the signals of different transmitting antennas are different. By using this speed difference, we can separate the signals of different transmitting antennas for a target at the receiving end.

[0076] The antenna module 60 includes but is not limited to an array antenna that supports a MIMO radar waveform using a DDMA waveform, and may also be implemented by other high-gain array antennas and wide-beam array antennas.

[0077] Figure 3 FIG. 2 is a schematic diagram of the module architecture of the second embodiment of the vehicle-mounted Doppler radar detection system of the present invention. Figure 3 As shown, the device of this embodiment is implemented as two devices, including a radar detection device U1 and a state analysis device U2. The radar detection device U1 is similar to the vehicle-mounted Doppler radar detection system of the first embodiment, including a radar transmitting and receiving module 10, a storage module 30, a main control module 40, a power management module 50 and an antenna module 60. However, the radar detection device U1 only retains the signal processing function in the detection module 20 of the first embodiment, that is, the detection module 20 is replaced by a signal processing submodule 201, and the feature analysis function in the detection module 20 of the first embodiment is placed in the state analysis device U2, and is implemented by the feature analysis submodule 202 of the state analysis device U2. In other words, the main functional module in the state analysis device U2 is the feature analysis submodule 202.

[0078] In addition, in order to realize data exchange between the radar detection device U1 and the state analysis device U2, the radar detection device U1 includes a first communication module 70, and the state analysis device U2 includes a second communication module 80. The first communication module 70 can establish a communication connection to realize data transmission.

[0079] The first communication module 70 is responsible for transmitting the radar beam reflection signal, processing result data (detection target status data) and / or intermediate processing result data obtained by the radar detection device U1 to the status analysis device U2 by wired or wireless means. Wireless standards include but are not limited to NFC (near field wireless communication technology), BT (Bluetooth), WIFI (wireless network communication technology), UWB, 2G / 3G / 4G / 5G / LTE and other mobile network technologies, FM (modulation communication technology), etc. Wired standards include but are not limited to optical fiber communication or other communication methods, including but not limited to commonly used SPI, I2C, Ethernet, UART and CAN-FD interfaces. The first communication module 70 and the second communication module both include but are not limited to the I / O interface of the mobile network, the I / O interface of the optical communication network and the I / O interface of other methods. The I / O interface of the device includes receiving data, transmitting data, and data packet forwarding at the network layer. Data packet forwarding can support various protocols (such as but not limited to TCP / IP, IPX / SPX, AppleTalk and other protocols).

[0080] like Figure 3 As shown, the state analysis device U2 in the second embodiment includes a feature analysis submodule 202 and a second communication module 80. In a specific implementation, the state analysis device U2 can be any device, apparatus or system with data receiving and processing functions, such as a PC, a server, a mobile terminal, a tablet computer, or even a cloud server.

[0081] It can be seen that the above embodiment of the present invention splits the functions of the detection module into two different devices, and separates the functions with large data processing volume, which can effectively reduce the work intensity of a single device and reduce the cost of a single device. At the same time, the state analysis device can establish a connection with at least two radar detection devices, thereby centrally processing and managing the data of multiple radar detection devices, thereby increasing the data processing and analysis capabilities. In other words, the radar detection devices of the vehicle-mounted Doppler radar detection system of this embodiment are at least two, and constitute a radar detection array.

[0082] Figure 4 FIG. 2 is a schematic diagram of the module architecture of the third embodiment of the vehicle-mounted Doppler radar detection system of the present invention. Figure 4As shown, the third embodiment is different from the second embodiment in that the detection module also includes an inertial navigation sensor submodule 203, that is, the detection module is implemented as a signal processing submodule 201 and an inertial navigation sensor submodule 203, and the inertial navigation sensor submodule 203 is used to detect the real-time position information of the radar detection device relative to the rail, and the real-time position information is used for the signal processing submodule to calibrate the radar data in real time. For example, the deviation caused by the vibration of the locomotive can be corrected in real time through the inertial navigation sensor data, and specifically can be calibrated with the CP III beside the rail within a certain distance. CP III is a pile control network, a three-dimensional control network laid along the line, the plane control starts and closes the basic plane control network (CPⅠ) or the line control network (CPⅡ), and the elevation control starts and closes the second-class leveling network laid along the line. It is generally measured after the offline engineering construction is completed, and it is the benchmark for the laying and operation and maintenance of ballastless track.

[0083] Figure 5 FIG. 4 is a schematic diagram of the module architecture of the fourth embodiment of the vehicle-mounted Doppler radar detection system of the present invention. Figure 5 As shown, this embodiment combines the architecture of the first embodiment with that of the second embodiment, that is, the radar detection device U1 and the state analysis device U2 both have complete data processing functions, the radar detection device U1 includes a first detection module 21, and the state analysis device includes a second detection module 22. The first detection module 21 and the second detection module 22 have the same functions as the detection module 20 of the first embodiment, and can perform independent data processing to obtain the state data of the detection target. At the same time, the radar detection device U1 and the state analysis device U2 can establish a communication connection.

[0084] In addition, the main control module 40 of the radar detection device U1 can also only transmit the collected state data of the detection target to the state analysis device U2 through the communication module 107, and the state analysis device U2 analyzes and processes it. The main control module 40 can even transmit a signal containing the judgment result to the state analysis device U2 through the first communication module 70, for example, only sending an alarm signal.

[0085] The radar detection device of the vehicle-mounted Doppler radar detection system of the fourth embodiment can either independently complete the detection or transmit the obtained radar data to the state analysis device, and the state analysis device completes the detection. The radar detection device can also choose to send the detected target state data to the state analysis device, or only send an alarm signal. The state analysis device can either independently process the state data, or directly receive the state data from the radar detection device, or directly receive the alarm signal. It can be seen that the third embodiment can expand the application scenario of the device of the present invention.

[0086] In addition, the radar detection device of the present invention supports data extraction in two states: independent working connection and no connection. In the no connection state, the Doppler radar device can realize data exchange through but not limited to NFC (near field wireless communication technology), BT (Bluetooth), infrared, WIFI (wireless network communication technology), UWB and the like. In the connection state, it supports but is not limited to data exchange through mobile networks such as 2G / 3G / 4G / 5G / LTE, or other ways of connecting to the Internet. The communication module 107 may include optical communication. The optical communication may be an optical fiber data transmission module. More specifically, the optical communication module may be a two-input and two-output optical fiber data transmission module to realize the self-healing ring network function.

[0087] Below through Figure 6 and Figure 7 To describe the specific implementation of the radar detection device for vehicle-mounted Doppler radar detection of the present invention, in the following embodiment, the radar detection device for vehicle-mounted Doppler radar detection is implemented as a vehicle-mounted Doppler radar detector. Figure 6 is an overall structural diagram of an embodiment of a vehicle-mounted Doppler radar detector of the present invention, Figure 7 2 is an exploded view of the internal structure of this embodiment.

[0088] like Figure 6 As shown, the vehicle-mounted Doppler radar detector of this embodiment is roughly in the shape of a rectangular parallelepiped, with an input and output interface on the shell, and a fixing structure for fixing the detector itself to other components.

[0089] like Figure 7 As shown in the exploded view, it can be seen that the detector includes a front shell assembly 11, a Doppler radar movement main board assembly 12, a Doppler radar transmit and receive control main board assembly 13, a communication module and I / O interface assembly 14, a Doppler radar antenna assembly 15, a power management module assembly 16 and a rear shell assembly 17.

[0090] The front shell assembly 11 and the rear shell assembly 17 are the main shells of the vehicle-mounted Doppler radar detector, which are used to install, fix and protect the Doppler radar movement main board assembly 12, the Doppler radar transmit and receive control main board assembly 13, the communication module and I / O interface 14, the Doppler radar antenna assembly 15, and the power management module assembly 16.

[0091] The Doppler radar core mainboard assembly 12 of this embodiment includes but is not limited to the Doppler radar device mainboard, the main control module and the storage module. In this embodiment, the main control module is implemented by the main chip MTK8878 microprocessor, but the present invention does not exclude the implementation of other devices with digital processing functions, such as FPGA, DSP, etc.

[0092] The Doppler radar transmitting and receiving control mainboard component 13 of this embodiment adopts a single-chip solution, for example, TI's chip AWR2944 is used to integrate the radar transmitting and receiving module 10 and the detection module 20 of the millimeter wave radar into one chip. In other embodiments, a single chip may also integrate a communication module 70. However, the present invention includes but is not limited to a single-chip solution, and the radar transmitting and receiving module 10 and the detection module 20 may also be designed in different chips and modules respectively, or multiple single-chip combined FMCW transceiver imaging radars may be used, depending on the specific implementation of the product.

[0093] The communication module and I / O interface 14 of this embodiment include a first communication module 70, which is responsible for transmitting the radar data and local operation data collected by the signal processing center to other devices or servers via wired or wireless methods. Wireless standards include but are not limited to NFC (near field communication technology), BT (Bluetooth), WIFI (wireless network communication technology), UWB, 2G / 3G / 4G / 5G / LTE and other mobile network technologies, FM (modulation communication technology), etc. Wired standards include but are not limited to optical fiber communication or other communications.

[0094] The I / O interface includes the I / O interface of the mobile network, the I / O interface of the optical communication network and other types of I / O interfaces. The I / O interface of the device includes receiving data, transmitting data, and packet forwarding at the network layer. Packet forwarding can support multiple protocols (such as but not limited to TCP / IP, IPX / SPX, AppleTalk) and other protocols.

[0095] The Doppler radar antenna assembly 15 of this embodiment includes but is not limited to an array consisting of 4 groups of radar transmitting antennas and 4 groups of radar receiving antennas. The radar antenna assembly 15 of this embodiment supports complex DDMA (Doppler diversity transmission) waveforms, and through the simultaneous transmission of multiple antennas of DDMA, combined with the detection signal chain of the millimeter wave receiving / transmitting module, a higher SNR (signal-to-noise ratio) and a longer detection distance are obtained, thereby comprehensively improving the performance of the radar.

[0096] The Doppler radar antenna assembly 15 of this embodiment includes but is not limited to a system combination of 4 transmit and 4 receive. According to the requirements, the number of combinations of radar transmit and receive antennas can be actually increased or decreased, and the number of virtual channels of the radar can be increased through MIMO (multiple input multiple output) technology, thereby improving the angular resolution of the radar.

[0097] The Doppler radar antenna assembly 15 of this embodiment includes but is not limited to an array antenna that supports a MIMO radar waveform using a DDMA waveform, and also includes other high-gain array antennas and wide-beam array antennas.

[0098] The power management module assembly 16 of this embodiment includes an external power supply and a built-in battery, and the external power port is any one of a DC-Jack mechanical structure or a USB, Micro USB, or USB Type C mechanical structure. The built-in battery is responsible for providing uninterrupted power when the device is not connected to an external power cord or when a power outage occurs during use.

[0099] The Doppler radar movement main board component 12, the Doppler radar transmission and reception control main board component 13, the communication module and the I / O interface 14 of this embodiment can be integrated into one main board component, or separated into multiple main board components.

[0100] Figure 8 The figure shows a cross-sectional view of the vehicle-mounted Doppler radar detector of the present invention installed at the bottom of the train and above the rails. In this embodiment, a row of 7 vehicle-mounted Doppler radar detectors U11, U12, ..., U17 are installed at the bottom of the train. The distance of each detector relative to the rails is fixed (the deviation of the locomotive vibration has been corrected in real time by the inertial navigation sensor data). When the vehicle-mounted Doppler radar detector passes over the rails at high speed with the train, it can detect the rapid changes of the sleepers C1, rails C2, fastener components C3, etc. relative to the radar radial depth information based on the rapid Doppler changes of each reflected beam, and generate and obtain the corresponding Doppler feature information.

[0101] Fig. 9 FIG. 1 is a schematic diagram of a fault in which a track plate rotates due to loosening of a track nail nut in an embodiment of the vehicle-mounted Doppler radar detector of the present invention. Fig. 9 It can be seen that when an abnormality occurs in fastener C3, different Doppler characteristic information will be fed back, thereby locating the abnormal state of the fastener.

[0102] Apart from Fig. 9 The monitoring and positioning of whether the fixed structural parts at the fixed positions on the track have displacement faults can also determine whether the structural parts are missing, and obtain partial information such as the qualitative nature of the material and size of the foreign matter being detected.

[0103] Preferably, the signal processing submodule of the vehicle-mounted Doppler radar detector of the present invention is also used to extract auxiliary feature information of the object under test based on the radar beam reflection signal received by the radar transmitting and receiving module, including information of distance, angle and reflection signal. These auxiliary feature information will also be processed by the feature analysis submodule to more accurately determine the state of the object under test.

[0104] Preferably, when processing Doppler feature information and auxiliary feature information, the present invention uses artificial intelligence deep learning to extract and analyze features. The deep learning data processing method includes collecting data from multiple radar detection devices on multiple trains, including characteristic values ​​of the health status of rails and roadbeds generated by the data collected by each train, statistically analyzing normal values ​​and abnormal values, establishing models and training models, and using the trained models to process new Doppler feature information and / or auxiliary feature information to calculate the state information of the object being measured. This can significantly improve the accuracy of judging foreign objects and abnormal movements, and normal and abnormal conditions on the track.

[0105] Fig.10 It is a detection flow diagram of the vehicle-mounted Doppler radar detector of the present invention.

[0106] Step F01: Install the Doppler radar device according to the embodiment of the present invention at an appropriate position on the bottom of the train. The selection of the position is related to the bottom structure of the train and its position relative to the track.

[0107] Step F02: Initialization settings, including time calibration, position calibration, normal orbit information, etc.

[0108] Step F03: While the vehicle is traveling at high speed, real-time Doppler characteristic information of the track and its environment is acquired in real time.

[0109] Step F04: Compare the Doppler characteristic information obtained in step F03 with the normal orbit information to determine the orbit health status result.

[0110] Step F05: Output the results. The results can be saved locally or uploaded to a designated device or cloud server in real time. The cloud server can be installed on the same vehicle (such as a high-speed train) or a distributed cloud server located in other places through a mobile network architecture. The server can perform further data processing and calculate the array radar signal to extract other feature information.

[0111] The vehicle-mounted Doppler radar detector of the embodiment of the present invention can be used alone, or multiple devices can be combined to form a system. For example, in practical applications, the following can be adopted: Fig.12 The design of installing two rows of radar detectors in parallel increases measurement redundancy and improves measurement accuracy. At the same time, in order to facilitate data processing, a host (state analysis device) can be set up in the train to interact with the above radar detection device (on-board Doppler radar detector) in real time, or a cloud server can be used to process the data.

[0112] Fig.11 It is a schematic diagram of the calculation process after multiple Doppler radars form a radar detection array. By optimizing the algorithm, the accuracy and reliability can be further improved.

[0113] like Fig.11 As shown, multiple vehicle-mounted Doppler radar detectors U11, U12, ..., U1n synchronously transmit and receive signals to obtain the characteristics of each radar transmission signal [1, 1], [2, 1], ..., [n, 1] and the characteristics of the radar reception signal [1, f], [2, f], ..., [n, f]. Based on this, each vehicle-mounted Doppler radar detector U11, U12, ..., U1n detects Doppler characteristic information P1, P2 ..., Pn. These Doppler characteristic information are transmitted to the cloud server C (the cloud server C is a specific implementation of the state analysis device U2), and the characteristics and state data S1, S2, ..., S7 of each detection target are obtained after processing by the cloud server C. Finally, fault judgment and alarm operations are performed on these state data (step H1). The present invention applies electromagnetic wave measurement technology to the detection of locomotive track and roadbed status, which not only utilizes the excellent characteristics of Doppler radar in measuring speed, but also avoids the difficulties brought by high-speed running trains to measurement, especially imaging. At the same time, with the maturity of millimeter-wave radar technology and the reduction of costs, specific products can fully use millimeter-wave radar sensors to achieve higher accuracy.

[0114] Although the present invention has been described above in conjunction with the exemplary embodiments and the accompanying drawings, it should be apparent to those skilled in the art that various modifications may be made to the above-described embodiments without departing from the spirit and scope of the claims.

Claims

1. A vehicle-mounted Doppler radar detection system, characterized in that: include: A radar transmitting and receiving module, which can be fixed to a rail vehicle and move along the track with the rail vehicle, and is used to transmit a radar beam to the track and receive a radar beam reflection signal during the movement along the track; a detection module, configured to process the radar beam reflection signal to obtain Doppler characteristic information of the radar beam reflection signal according to the Doppler effect of each radar reflection beam, and judge the state of the detection target according to the Doppler characteristic information, wherein the Doppler characteristic information is obtained by comparing the current radar beam reflection signal with the standard radar beam signal; The detection module and the radar transmitting and receiving module are integrated in the same device, which is fixed to the rail vehicle and moves along the track with the rail vehicle; The detection module includes a signal processing submodule and a feature analysis submodule. The signal processing submodule is used to pre-process the radar beam reflection signal to generate radar data; The feature analysis submodule is used to analyze the radar data to obtain the Doppler feature information, and process the Doppler feature information according to the trained deep learning model to calculate the state information of the object under test, so as to monitor the current health status of the track and roadbed of the rail vehicle and its long-term change trend, wherein the deep learning model is obtained by collecting radar data from multiple radar detection devices on multiple trains and training feature data of the health status of the rails and roadbed generated according to the respectively collected data.

2. The vehicle-mounted Doppler radar detection system as claimed in claim 1, characterized in that: It includes a radar detection device and a state analysis device capable of information exchange. The signal processing submodule and the radar transmitting and receiving module are integrated in the radar detection device, and the radar detection device is fixed to the rail vehicle and moves along the track with the rail vehicle; The feature analysis submodule is integrated into the state analysis device.

3. The vehicle-mounted Doppler radar detection system as claimed in claim 2, characterized in that: The status analysis device is a cloud server.

4. The vehicle-mounted Doppler radar detection system as claimed in claim 2, characterized in that: The radar detection device and the state analysis device both include a communication module, so that the radar detection device and the state analysis device communicate with each other through the communication module.

5. The vehicle-mounted Doppler radar detection system as claimed in claim 4, characterized in that: There are at least two radar detection devices, which form a radar detection array; the state analysis device can communicate with each radar detection device in the radar detection array through the communication module.

6. The vehicle-mounted Doppler radar detection system as claimed in claim 5, characterized in that: The radar detection device is also integrated with an antenna module, which serves as the antenna of the radar transmitting and receiving module.

7. The vehicle-mounted Doppler radar detection system as claimed in claim 6, characterized in that: When the radar detection device is used to form a radar detection array, the antenna module is a MIMO antenna module.

8. The vehicle-mounted Doppler radar detection system as claimed in claim 1, characterized in that: The detection module also includes an inertial navigation sensor submodule, which is used to detect the real-time position information of the radar detection device relative to the rail. The real-time position information is used by the signal processing submodule to calibrate the radar data in real time.

9. The vehicle-mounted Doppler radar detection system as claimed in claim 1, characterized in that: The signal processing submodule is also used to extract auxiliary feature information according to the radar beam reflection signal received by the radar transmitting and receiving module; The feature analysis submodule determines the state of the detection target according to the Doppler feature information and the auxiliary feature information.

10. The vehicle-mounted Doppler radar detection system according to any one of claims 2 to 9, characterized in that: The radar detection device is further integrated with a storage module, which is used to store the radar beam reflection signal and / or radar data generated by the radar beam reflection signal.

11. The vehicle-mounted Doppler radar detection system according to any one of claims 2 to 9, characterized in that: The radar detection device is also integrated with a main control module, which is used to control the operations of other modules.

12. The vehicle-mounted Doppler radar detection system according to any one of claims 2 to 9, characterized in that: The radar detection device is also integrated with a power management module, which is used to provide power to each module in the radar detection device.

13. A vehicle-mounted Doppler radar detection array, characterized in that: The invention is composed of a plurality of radar detection devices installed on the same rail vehicle, wherein the radar detection device is the radar detection device described in any one of claims 2 to 9.

14. A vehicle-mounted Doppler radar detection method, characterized in that: include: The radar transmitting and receiving module and the detection module are fixed to the rail vehicle and move along the track with the rail vehicle; During the movement along the track, the radar transmitting and receiving module transmits a radar beam to the track and receives a reflected signal of the radar beam; Using a detection module to process the radar beam reflection signal to obtain Doppler feature information of the radar beam reflection signal according to the Doppler effect of each radar reflection beam, and using a trained deep learning model to process the Doppler feature information to determine the state of the detection target, so as to monitor the current health state of the track and roadbed of the rail vehicle and its long-term change trend; The Doppler characteristic information is obtained by comparing the current radar beam reflection signal with the standard radar beam signal. The deep learning model is obtained by collecting radar data from multiple radar detection devices on multiple trains and training feature data on the health status of rails and roadbeds generated based on the respectively collected data.

15. The vehicle-mounted Doppler radar detection method according to claim 14, characterized in that: The radar transmitting and receiving modules are radar transmitting and receiving modules from multiple radar detection devices, and the radar beam reflection signals are array signals received by the multiple radar transmitting and receiving modules.

Images